A system comprising a database and a user device. The database may be configured to (i) store metadata generated in response to objects detected in a video, (ii) store a confidence level associated with the metadata, (iii) provide to a plurality of users (a) data portions of the video and (b) a request for feedback, (iv) receive the feedback and (v) update the confidence level associated with the metadata in response to the feedback. The user device may be configured to (i) view the data portions, (ii) accept input to receive the feedback from one of said plurality of users and (iii) communicate the feedback to the database. The confidence level may indicate a likelihood of correctness of the objects detected in response to video analysis performed on the video. The database may track user statistics for the plurality of users based on the feedback.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A system comprising: a database configured to (i) store metadata generated in response to objects detected in a video generated by a capture device and a data portion of said video associated with said metadata, (ii) store a confidence level associated with said metadata, (iii) provide to a plurality of users (a) said data portion of said video and (b) a request for feedback, (iv) receive said feedback based on the request, (v) update said confidence level associated with said metadata in response to said feedback, and (vi) apply a statistical weight to said feedback for each user of said users when updating said confidence level associated with said metadata; and a user device comprising a processor, said user device configured to (i) display said data portion of said video, (ii) accept input for said data portion to receive said feedback from one of said plurality of users and (iii) communicate said feedback to said database, wherein (a) said confidence level indicates a likelihood of correctness of said objects detected in response to video analysis performed on said video by said capture device based on machine learning, (b) said machine learning (i) is configured to enable said capture device to generate object detection results and (ii) enables said object detection results to be improved in response to said feedback, (c) said database tracks user statistics for said plurality of users based on said feedback, (d) said user statistics comprise a trust level for each user of said plurality of users, (e) said trust level is based on whether said feedback previously provided by one of said users is determined to be correct, (f) said user statistics are presented to said user device to provide a competition between said users, (g) said competition provides a gamified experience to encourage said users to provide said feedback about said video analysis performed by said capture device, (h) said feedback updates said confidence level to correct results of said video analysis for said capture device, (i) a rank is provided separately for each category of a plurality of categories to enable said competition separately for each category of said plurality of categories and (j) said rank for each user of said plurality of users is based on said user statistics.
2. The system according to claim 1 , wherein said user device is implemented as a smartphone.
3. The system according to claim 1 , wherein (i) said user device is implemented as a smart watch and (ii) said smart watch is configured to enable at least one of Wi-Fi and cellular communication.
4. The system according to claim 1 , wherein said user device does not display said data portion or receive said feedback when one of said users associated with said user device is driving.
5. The system according to claim 1 , wherein (i) said database is configured to generate a query comprising said data portion and said request for said feedback and (ii) said user device is configured to display a gamification interface configured to display said data portion and receive said feedback about said correctness of said objects detected in response to said video analysis.
6. The system according to claim 5 , wherein said gamification interface is configured to present said query with a yes response and a no response.
7. The system according to claim 6 , wherein (i) said gamification interface presents a blank text field to enable one of said users to enter a correction for said objects detected in response to said video analysis and (ii) said correction is presented to said database as said feedback.
8. The system according to claim 5 , wherein (i) said gamification interface is configured to present said query with multiple choice options and (ii) said multiple choice options are generated based on a plurality of confidence levels associated with potential results from said video analysis.
9. The system according to claim 1 , wherein said statistical weight for one of said users is associated with said trust level for said one of said users.
10. The system according to claim 1 , wherein said database is configured to penalize each user of said plurality of users when said trust level is low.
11. The system according to claim 1 , wherein said user statistics comprise a score for each user of said plurality of users.
12. The system according to claim 11 , wherein said database is configured to provide a leaderboard configured to display said rank for each user of said plurality of users based on said score.
13. The system according to claim 12 , wherein (i) said leaderboard comprises said plurality of categories of said objects detected.
14. The system according to claim 12 , wherein said database is configured to provide perks for each user of said plurality of users based on said rank.
15. The system according to claim 1 , wherein (i) said feedback from each user of said plurality of users is aggregated by said database and (ii) said aggregated feedback is used for training said video analysis.
16. The system according to claim 1 , wherein said objects comprise at least one of a license plate, individual license plate characters, vehicles, street signs, traffic lights, pedestrians or roadway characteristics.
17. The system according to claim 1 , wherein (i) said database is configured to correct previously stored metadata based on said update of said confidence level and (ii) said feedback provides a disparate source of data to enable the system to infer results that would be unable to be determined from one source alone.
18. The system according to claim 1 , wherein said metadata comprises information extracted by said capture device from said video without said database storing each video frame of said video captured by said capture device.
19. The system according to claim 1 , wherein said gamified experience provides an incentive to solicit human input as said feedback.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
November 21, 2018
May 18, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.